[PATCH Linux v6 10/10] xen/privcmd: Add new ABI to allow copying foreign memory

This new ABI allows to copy foreign domain memory to/from a buffer.
This avoids having to map/copy/unmap foreign memory which is
expensive.
This operation is done particularly when migrating VMs.

Signed-off-by: Frediano Ziglio <[email protected]>
--
Changes since v4:
- fix wrong assign;
- use set_xen_guest_handle to set handle;
- wrap slow hypercall with xen_preemptible_hcall_{begin,end};
- use _IOWR for ioctl code to be more specific;
- use __copy_to_user if buffer already checked.

Changes since v6:
- compatibility ARM/x86.

---
 arch/x86/include/asm/xen/interface.h |  3 ++
 drivers/xen/privcmd.c                | 49 ++++++++++++++++++++++++++++
 include/uapi/xen/privcmd.h           | 10 ++++++
 include/xen/arm/interface.h          |  2 ++
 include/xen/interface/memory.h       | 37 +++++++++++++++++++++
 5 files changed, 101 insertions(+)

diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index a078a2b0f032..fc76fac8fb16 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -59,6 +59,7 @@
 #elif defined(__x86_64__)
 #define set_xen_guest_handle(hnd, val)	do { (hnd).p = val; } while (0)
 #endif
+#define get_xen_guest_handle(hnd) ((hnd).p)
 #else
 #if defined(__i386__)
 #define set_xen_guest_handle(hnd, val)			\
@@ -70,6 +71,7 @@
 #elif defined(__x86_64__)
 #define set_xen_guest_handle(hnd, val)	do { (hnd) = val; } while (0)
 #endif
+#define get_xen_guest_handle(hnd) (hnd)
 #endif
 
 #ifndef __ASSEMBLER__
@@ -91,6 +93,7 @@ DEFINE_GUEST_HANDLE(int);
 DEFINE_GUEST_HANDLE(void);
 DEFINE_GUEST_HANDLE(uint64_t);
 DEFINE_GUEST_HANDLE(uint32_t);
+DEFINE_GUEST_HANDLE(uint8_t);
 DEFINE_GUEST_HANDLE(xen_pfn_t);
 DEFINE_GUEST_HANDLE(xen_ulong_t);
 #endif
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 725a49a0eee7..55364801ba2e 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -1522,6 +1522,51 @@ static inline void privcmd_ioeventfd_exit(void)
 }
 #endif /* CONFIG_XEN_PRIVCMD_EVENTFD */
 
+static long privcmd_ioctl_foreigncopy(
+	struct file *file, void __user *udata)
+{
+	const struct privcmd_data *const data = file->private_data;
+	long ret;
+	struct privcmd_foreigncopy copy;
+	struct xen_foreigncopy xcopy;
+
+	if (copy_from_user(&copy, udata, sizeof(copy)))
+		return -EFAULT;
+	if (copy.dir & ~1u)
+		return -EINVAL;
+	if (copy.num >= U32_MAX >> PAGE_SHIFT)
+		return -EINVAL;
+	if (!access_ok(copy.pfns, copy.num * sizeof(*copy.pfns)))
+		return -EFAULT;
+	if (!access_ok(copy.buffer, copy.num << PAGE_SHIFT))
+		return -EFAULT;
+
+	/* If restriction is in place, check the domid matches */
+	if (data->domid != DOMID_INVALID && data->domid != copy.dom)
+		return -EPERM;
+
+	xcopy.domid = copy.dom;
+	xcopy.flags = copy.dir;
+	xcopy.nr_frames = copy.num;
+	set_xen_guest_handle(xcopy.frame_list,  (__force xen_pfn_t *)copy.pfns);
+	set_xen_guest_handle(xcopy.buffer, (__force uint8_t *)copy.buffer);
+
+	xen_preemptible_hcall_begin();
+	ret = HYPERVISOR_memory_op(XENMEM_foreigncopy, &xcopy);
+	xen_preemptible_hcall_end();
+
+	/* copy values back in case of error */
+	if (ret) {
+		copy.num = xcopy.nr_frames;
+		copy.pfns = get_xen_guest_handle(xcopy.frame_list);
+		copy.buffer = get_xen_guest_handle(xcopy.buffer);
+		if (__copy_to_user(udata, &copy, sizeof(copy)))
+			ret = -EFAULT;
+	}
+
+	return ret;
+}
+
 static long privcmd_ioctl(struct file *file,
 			  unsigned int cmd, unsigned long data)
 {
@@ -1569,6 +1614,10 @@ static long privcmd_ioctl(struct file *file,
 		ret = privcmd_ioctl_pcidev_get_gsi(file, udata);
 		break;
 
+	case IOCTL_PRIVCMD_FOREIGNCOPY:
+		ret = privcmd_ioctl_foreigncopy(file, udata);
+		break;
+
 	default:
 		break;
 	}
diff --git a/include/uapi/xen/privcmd.h b/include/uapi/xen/privcmd.h
index 8e2c8fd44764..993b501e35bf 100644
--- a/include/uapi/xen/privcmd.h
+++ b/include/uapi/xen/privcmd.h
@@ -131,6 +131,14 @@ struct privcmd_pcidev_get_gsi {
 	__u32 gsi;
 };
 
+struct privcmd_foreigncopy {
+	domid_t dom;		/* foreign domain */
+	__u16 dir;		/* direction,  0 from, 1 to */
+	__u32 num;		/* number of pages to copy */
+	const xen_pfn_t __user *pfns;	/* array of pfns */
+	void __user *buffer;	/* buffer to copy to/from */
+};
+
 /*
  * @cmd: IOCTL_PRIVCMD_HYPERCALL
  * @arg: &privcmd_hypercall_t
@@ -164,5 +172,7 @@ struct privcmd_pcidev_get_gsi {
 	_IOW('P', 9, struct privcmd_ioeventfd)
 #define IOCTL_PRIVCMD_PCIDEV_GET_GSI				\
 	_IOC(_IOC_NONE, 'P', 10, sizeof(struct privcmd_pcidev_get_gsi))
+#define IOCTL_PRIVCMD_FOREIGNCOPY				\
+	_IOWR('P', 11, struct privcmd_foreigncopy)
 
 #endif /* __LINUX_PUBLIC_PRIVCMD_H__ */
diff --git a/include/xen/arm/interface.h b/include/xen/arm/interface.h
index 61360b89da40..20ee1ed44436 100644
--- a/include/xen/arm/interface.h
+++ b/include/xen/arm/interface.h
@@ -27,6 +27,7 @@
 			*(uint64_t *)&(hnd) = 0;	\
 		(hnd).p = val;				\
 	} while (0)
+#define get_xen_guest_handle(hnd) ((hnd).p)
 
 #define __HYPERVISOR_platform_op_raw __HYPERVISOR_platform_op
 
@@ -53,6 +54,7 @@ DEFINE_GUEST_HANDLE(int);
 DEFINE_GUEST_HANDLE(void);
 DEFINE_GUEST_HANDLE(uint64_t);
 DEFINE_GUEST_HANDLE(uint32_t);
+DEFINE_GUEST_HANDLE(uint8_t);
 DEFINE_GUEST_HANDLE(xen_pfn_t);
 DEFINE_GUEST_HANDLE(xen_ulong_t);
 
diff --git a/include/xen/interface/memory.h b/include/xen/interface/memory.h
index 1a371a825c55..5981402fccde 100644
--- a/include/xen/interface/memory.h
+++ b/include/xen/interface/memory.h
@@ -325,4 +325,41 @@ struct xen_mem_acquire_resource {
 };
 DEFINE_GUEST_HANDLE_STRUCT(xen_mem_acquire_resource);
 
+/*
+ * Copy memory from/to a given domain.
+ */
+#define XENMEM_foreigncopy 29
+struct xen_foreigncopy {
+    /* IN - The domain whose resource is to be copied */
+    domid_t domid;
+
+    /* IN - Flags */
+#define XENMEM_foreigncopy_from 0
+#define XENMEM_foreigncopy_to 1
+#define XENMEM_foreigncopy_direction 1
+    uint16_t flags;
+
+    /*
+     * IN
+     *
+     * As an IN parameter number of frames of the domain to be copied.
+     */
+    uint32_t nr_frames;
+
+    /*
+     * IN
+     *
+     * Frames to be copied.
+     */
+    GUEST_HANDLE(xen_pfn_t) frame_list;
+
+    /*
+     * IN/OUT
+     *
+     * Userspace buffer to read/write from.
+     */
+    GUEST_HANDLE(uint8_t) buffer;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_foreigncopy);
+
 #endif /* __XEN_PUBLIC_MEMORY_H__ */
-- 
2.54.0